Dual Deep Network for Visual Tracking

Abstract

Visual tracking addresses the problem of identifying and localizing an unknown target in a video given the target specified by a bounding box in the first frame. In this paper, we propose a dual network to better utilize features among layers for visual tracking. It is observed that features in higher layers encode semantic context while its counterparts in lower layers are sensitive to discriminative appearance. Thus we exploit the hierarchical features in different layers of a deep model and design a dual structure to obtain better feature representation from various streams, which is rarely investigated in previous work. To highlight geometric contours of the target, we integrate the hierarchical feature maps with an edge detector as the coarse prior maps to further embed local details around the target. To leverage the robustness of our dual network, we train it with random patches measuring the similarities between the network activation and target appearance, which serves as a regularization to enforce the dual network to focus on target object. The proposed dual network is updated online in a unique manner based on the observation that the target being tracked in consecutive frames should share more similar feature representations than those in the surrounding background. It is also found that for a target object, the prior maps can help further enhance performance by passing message into the output maps of the dual network. Therefore, an independent component analysis with reference algorithm (ICA-R) is employed to extract target context using prior maps as guidance. Online tracking is conducted by maximizing the posterior estimate on the final maps with stochastic and periodic update. Quantitative and qualitative evaluations on two large-scale benchmark data sets show that the proposed algorithm performs favourably against the state-of-the-arts.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• High-Speed Tracking with Kernelized Correlation Filters
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network
• Inner and Inter Label Propagation: Salient Object Detection in the Wild
• Video Tracking Using Learned Hierarchical Features
• Multi-Bias Non-linear Activation in Deep Neural Networks

Cited by in corpus (15)

• Deep Learning for Visual Tracking: A Comprehensive Survey
• Rethinking Feature Discrimination and Polymerization for Large-scale Recognition
• Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivity
• Siamese Attentional Keypoint Network for High Performance Visual Tracking
• Learning Deep Features via Congenerous Cosine Loss for Person Recognition
• NoScope: Optimizing Neural Network Queries over Video at Scale
• Parallel Tracking and Verifying
• Siamese Cascaded Region Proposal Networks for Real-Time Visual Tracking
• A Review of Visual Trackers and Analysis of its Application to Mobile Robot
• Coarse-to-Fine Object Tracking Using Deep Features and Correlation Filters
• Visual Tracking via Dynamic Memory Networks
• High Speed Tracking With A Fourier Domain Kernelized Correlation Filter
• FPAN: Fine-grained and Progressive Attention Localization Network for Data Retrieval
• Rethinking Convolutional Features in Correlation Filter Based Tracking
• Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends